Menu
Sign In Search Podcasts Charts People & Topics Add Podcast API Blog Pricing

Morgan Linton

๐Ÿ‘ค Speaker
666 total appearances

Appearances Over Time

Podcast Appearances

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

Then you can just run Cloud in the terminal and you're good.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

For people that are using the API, the one thing I did want to point out is there's a pretty cool new addition, which is called Adaptive Thinking.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

also just to be clear because i'm seeing confusion on this too this is in the api this is not in cloud code itself but adaptive thinking just to show it here you're able to essentially pick the level of effort that you would like the model to use this is only going to work in four six by the way if you want to use like an effort level of max

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

And so here's kind of the different levels.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

So with Max, Claude always thinks with no constraints on thinking depth.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

It's Opus 4.6 only.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

So requests using Max on other models are going to return an error.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

So if you're calling the API and you set the effort level to Max and you get an error, then you're probably not

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

using Opus 4.6.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

But here's the example where you can see if I'm calling the API, I set the model to Cloud Opus 4.6.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

And then here's where I can set the effort.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

And this is another thing.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

If you're using existing API code, you may have the model of Opus 4.5.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

And now you adjust the effort to max.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

It gives you an error.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

All you need to do is just bump the version and you're good.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

But this is kind of a neat thing they've added to the API with 4.6 that's worth mentioning.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

And then kind of the last thing I would say is just if you want to use split panes for agents.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

So if you want agents to show up in different panes and you're using something like warp, just make sure to install tmux.

The Startup Ideas Podcast
Claude Opus 4.6 vs GPT-5.3 Codex: Live Build, Clear Winner

You can do this with brew install tmux.